Relationships Between the A Priori and A Posteriori Errors in Nonlinear Adaptive Neural Filters
Keyword(s):
A Priori
◽
The lower bounds for the a posteriori prediction error of a nonlinear predictor realized as a neural network are provided. These are obtained for a priori adaptation and a posteriori error networks with sigmoid nonlinearities trained by gradient-descent learning algorithms. A contractivity condition is imposed on a nonlinear activation function of a neuron so that the a posteriori prediction error is smaller in magnitude than the corresponding a priori one. Furthermore, an upper bound is imposed on the learning rate η so that the approach is feasible. The analysis is undertaken for both feedforward and recurrent nonlinear predictors realized as neural networks.
2011 ◽
pp. 280-305
◽
2017 ◽
Vol 327
◽
pp. 4-35
◽
2021 ◽
2018 ◽
Vol 75
(4)
◽
pp. 1191-1212
◽
2004 ◽
Vol 30
(5)
◽
pp. 278-294
◽